Spoken Question Answering on Web Questions
44.59AccuracyFun-Audio-Chat-8B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Fun-Audio-Chat-8BModality=S2T2026.04 | 44.59 | — | — | |
| FreezeEmpathModality=S2T2026.04 | 44.34 | — | — | |
| Kimi-AudioModality=S2T2026.04 | 43.01 | — | — | |
| Fun-Audio-Chat-8BModality=S2S2026.04 | 42.47 | — | — | |
| FreezeEmpathModality=S2S2026.04 | 39.42 | — | — | |
| Kimi-AudioModality=S2S2026.04 | 36.52 | — | — | |
| Step-Audio2-MiniModality=S2T2026.04 | 35.53 | — | — | |
| Step-Audio2-MiniModality=S2S2026.04 | 34.89 | — | — | |
| LLaMA-Omni2-7BModality=S2T2026.04 | 34.69 | — | — | |
| LLaMA-Omni2-7BModality=S2S2026.04 | 31.5 | — | — | |
| OpenS2SModality=S2T2026.04 | 30.41 | — | — | |
| OpenS2SModality=S2S2026.04 | 24.16 | — | — | |
| Baichuan-Omni-1.5Parameters=7B2026.03 | — | 45.58 | 4.32 | |
| Freeze-OmniParameters=7B2026.03 | — | 47.31 | 4.23 | |
| GLM-4-VoiceParameters=9B2026.03 | — | 10.16 | 4.11 | |
| LLaMA-Omni2Parameters=7B2026.03 | — | 5.75 | 4.43 | |
| Qwen2.5-Omni-7BParameters=7B2026.03 | — | 1.68 | 4.32 | |
| SPEECH-OMNI-LITEParameters=8B2026.03 | — | 22.55 | 3.96 | |
| VocalNetParameters=8B2026.03 | — | 5.01 | 4.49 |